mlsanityData to 7 Oct 2026

Evaluating and Understanding the Robustness of Adversarial Logit Pairing

arXiv 1807.10272 ↗First posted 26 Jul 2018stat.ML cs.CR cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing achieves 0.6% accuracy in the threat model in which the defense is considered. We provide a brief overview of the defense and the threat models/claims considered, as well as a discussion of the methodology and results of our attack, which may offer insights into the reasons underlying the vulnerability of ALP to adversarial attack.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 6; 2023: 5; 2024: 5; 2025: 7; 2026: 1.

34 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  2. 2021Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimizationcited by 75
  3. 2021On the effectiveness of adversarial training against common corruptionscited by 71
  4. 2022Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 42
  5. 2022Sparsity Winning Twice: Better Robust Generalization from More Efficient Trainingcited by 41
  6. 2021Reliably fast adversarial training via latent adversarial perturbationcited by 29
  7. 2023Randomized Adversarial Training via Taylor Expansioncited by 28
  8. 2022Fairify: Fairness Verification of Neural Networkscited by 22
  9. 2021Generating Adversarial Computer Programs using Optimized Obfuscationscited by 20
  10. 2022Improving Robustness by Enhancing Weak Subnetscited by 12
  11. 2025Enhancing Robust Fairness via Confusional Spectral Regularizationcited by 11
  12. 2025Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustnesscited by 9
22 more
  1. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  2. 2021Robustness through Data Augmentation Loss Consistencycited by 8
  3. 2023Annealing Self-Distillation Rectification Improves Adversarial Trainingcited by 7
  4. 2025A Survey on Unlearnable Datacited by 5
  5. 2025Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Losscited by 5
  6. 2022A3T: Accuracy Aware Adversarial Trainingcited by 4
  7. 2023Revisiting adversarial training for the worst-performing classcited by 4
  8. 2023Enhancing Adversarial Training via Reweighting Optimization Trajectorycited by 4
  9. 2021Smoothness Analysis of Adversarial Trainingcited by 2
  10. 2021Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networkscited by 2
  11. 2023Label Smoothing is Robustification against Model Misspecificationcited by 2
  12. 2021THAT: Two Head Adversarial Training for Improving Robustness at Scalecited by 1
  13. 2024RAMP: Boosting Adversarial Robustness Against Multiple lp Perturbations for Universal Robustnesscited by 1
  14. 2024Adversarial Robustness Overestimation and Instability in TRADEScited by 1
  15. 2025Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligencecited by 1
  16. 2025LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metricscited by 1
  17. 2022Critical Checkpoints for Evaluating Defence Models Against Adversarial Attack and Robustnesscited by 0
  18. 2024Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attackscited by 0
  19. 2024Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selectioncited by 0
  20. 2024Standard-Deviation-Inspired Regularization for Improving Adversarial Robustnesscited by 0
  21. 2025Sy-FAR: Symmetry-based Fair Adversarial Robustnesscited by 0
  22. 2026S2O: Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 0